{"id":"https://openalex.org/W2913618459","doi":"https://doi.org/10.1109/tmm.2019.2896516","title":"Know More Say Less: Image Captioning Based on Scene Graphs","display_name":"Know More Say Less: Image Captioning Based on Scene Graphs","publication_year":2019,"publication_date":"2019-01-30","ids":{"openalex":"https://openalex.org/W2913618459","doi":"https://doi.org/10.1109/tmm.2019.2896516","mag":"2913618459"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2019.2896516","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2896516","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100341799","display_name":"Xiangyang Li","orcid":"https://orcid.org/0000-0002-3944-4704"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyang Li","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3944-4704","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085719285","display_name":"Shuqiang Jiang","orcid":"https://orcid.org/0000-0002-1596-4326"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuqiang Jiang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1596-4326","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":14.0617,"has_fulltext":false,"cited_by_count":198,"citation_normalized_percentile":{"value":0.99312797,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"21","issue":"8","first_page":"2117","last_page":"2130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.929794430732727},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.848751962184906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6607382297515869},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6235873103141785},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6177957057952881},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6161144375801086},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5500442385673523},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5407078862190247},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.4851130247116089},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4580913484096527},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4537045359611511},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45047271251678467},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.4486241936683655},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44789817929267883},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4318027198314667},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.4127451181411743},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4056198000907898},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3729502558708191}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.929794430732727},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.848751962184906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6607382297515869},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6235873103141785},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6177957057952881},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6161144375801086},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5500442385673523},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5407078862190247},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.4851130247116089},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4580913484096527},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4537045359611511},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45047271251678467},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.4486241936683655},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44789817929267883},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4318027198314667},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.4127451181411743},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4056198000907898},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3729502558708191},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2019.2896516","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2896516","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G2975255100","display_name":null,"funder_award_id":"L182054","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G3605299792","display_name":"\u8de8\u7f51\u4e92\u8054\u89c6\u97f3\u9891\u5173\u8054\u5206\u6790\u4e0e\u641c\u7d22","funder_award_id":"61532018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":118,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W825973156","https://openalex.org/W950853366","https://openalex.org/W1514535095","https://openalex.org/W1517303303","https://openalex.org/W1522301498","https://openalex.org/W1536680647","https://openalex.org/W1686810756","https://openalex.org/W1785460851","https://openalex.org/W1811254738","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1923211482","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W2022398331","https://openalex.org/W2077069816","https://openalex.org/W2092399515","https://openalex.org/W2101105183","https://openalex.org/W2117539524","https://openalex.org/W2127795553","https://openalex.org/W2133512280","https://openalex.org/W2133564696","https://openalex.org/W2144499799","https://openalex.org/W2144715671","https://openalex.org/W2153579005","https://openalex.org/W2154652894","https://openalex.org/W2157331557","https://openalex.org/W2176091656","https://openalex.org/W2194775991","https://openalex.org/W2220981600","https://openalex.org/W2277195237","https://openalex.org/W2302086703","https://openalex.org/W2316082076","https://openalex.org/W2339652278","https://openalex.org/W2342543219","https://openalex.org/W2479423890","https://openalex.org/W2506483933","https://openalex.org/W2526273376","https://openalex.org/W2550553598","https://openalex.org/W2552161745","https://openalex.org/W2558834163","https://openalex.org/W2564590796","https://openalex.org/W2575842049","https://openalex.org/W2579549467","https://openalex.org/W2591644541","https://openalex.org/W2605736949","https://openalex.org/W2607855566","https://openalex.org/W2613718673","https://openalex.org/W2616969219","https://openalex.org/W2745461083","https://openalex.org/W2749708282","https://openalex.org/W2754689878","https://openalex.org/W2766237723","https://openalex.org/W2766375149","https://openalex.org/W2767057417","https://openalex.org/W2792265253","https://openalex.org/W2795151422","https://openalex.org/W2805984364","https://openalex.org/W2949376505","https://openalex.org/W2951183276","https://openalex.org/W2951824008","https://openalex.org/W2962737704","https://openalex.org/W2962779575","https://openalex.org/W2962811161","https://openalex.org/W2962968835","https://openalex.org/W2963037989","https://openalex.org/W2963084599","https://openalex.org/W2963184176","https://openalex.org/W2963389687","https://openalex.org/W2963536419","https://openalex.org/W2963630207","https://openalex.org/W2963649796","https://openalex.org/W2963650529","https://openalex.org/W2963686907","https://openalex.org/W2963726321","https://openalex.org/W2963762755","https://openalex.org/W2963800628","https://openalex.org/W2963846044","https://openalex.org/W2963923113","https://openalex.org/W2964018924","https://openalex.org/W2964049455","https://openalex.org/W2964121744","https://openalex.org/W2964199361","https://openalex.org/W2964308564","https://openalex.org/W3099884890","https://openalex.org/W3102566412","https://openalex.org/W3103022576","https://openalex.org/W4294170691","https://openalex.org/W6630875275","https://openalex.org/W6631097402","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6638167273","https://openalex.org/W6638742206","https://openalex.org/W6639694449","https://openalex.org/W6678830454","https://openalex.org/W6679434410","https://openalex.org/W6681516684","https://openalex.org/W6682631176","https://openalex.org/W6682691769","https://openalex.org/W6714414533","https://openalex.org/W6721769334","https://openalex.org/W6725318829","https://openalex.org/W6727393572","https://openalex.org/W6729046916","https://openalex.org/W6738090124","https://openalex.org/W6742999658","https://openalex.org/W6746003159","https://openalex.org/W6746101150","https://openalex.org/W6746826305","https://openalex.org/W6748412295","https://openalex.org/W6749280594","https://openalex.org/W6749731246","https://openalex.org/W6750771589","https://openalex.org/W6751885507"],"related_works":["https://openalex.org/W3192357901","https://openalex.org/W3036286480","https://openalex.org/W2387360586","https://openalex.org/W4287027631","https://openalex.org/W4237171675","https://openalex.org/W3209723314","https://openalex.org/W2952736415","https://openalex.org/W3205398323","https://openalex.org/W2883297582","https://openalex.org/W2962677013"],"abstract_inverted_index":{"Automatically":[0],"describing":[1],"the":[2,14,19,71,141,191],"content":[3,20],"of":[4,21,70,145,193],"an":[5,22],"image":[6,88,102],"has":[7,66],"been":[8,67],"attracting":[9],"considerable":[10],"research":[11],"attention":[12],"in":[13,76,117,132],"multimedia":[15],"field.":[16],"To":[17,124],"represent":[18],"image,":[23],"many":[24],"approaches":[25,49],"directly":[26],"utilize":[27],"convolutional":[28],"neural":[29,41],"networks":[30,42],"(CNNs)":[31],"to":[32,43,173],"extract":[33,137,152],"visual":[34,127,149],"representations,":[35,150],"which":[36],"are":[37],"fed":[38],"into":[39,60],"recurrent":[40],"generate":[44],"natural":[45],"language.":[46],"Recently,":[47],"some":[48],"have":[50],"detected":[51],"semantic":[52,130,153,162],"concepts":[53],"from":[54,140,156],"images":[55,77,118],"and":[56,129,151],"then":[57],"encoded":[58],"them":[59],"high-level":[61],"representations.":[62,163],"Although":[63],"substantial":[64],"progress":[65],"achieved,":[68],"most":[69],"previous":[72],"methods":[73],"treat":[74],"entities":[75,116,147],"individually,":[78],"thus":[79],"lacking":[80],"structured":[81,108,133],"information":[82,109],"that":[83],"provides":[84],"important":[85],"cues":[86],"for":[87,101,148,161,177],"captioning.":[89,103],"In":[90],"this":[91],"paper,":[92],"we":[93,136,168],"propose":[94],"a":[95,170],"framework":[96],"based":[97],"on":[98,187],"scene":[99,134],"graphs":[100,105],"Scene":[104],"contain":[106],"abundant":[107],"because":[110],"they":[111],"not":[112],"only":[113],"depict":[114],"object":[115,146],"but":[119],"also":[120],"present":[121],"pairwise":[122],"relationships.":[123],"leverage":[125],"both":[126],"features":[128,139,155,176],"knowledge":[131],"graphs,":[135],"CNN":[138],"bounding":[142],"box":[143],"offsets":[144],"relationship":[154],"triples":[157],"(e.g.,man":[158],"riding":[159],"bike)":[160],"After":[164],"obtaining":[165],"these":[166],"features,":[167],"introduce":[169],"hierarchical-attention-based":[171],"module":[172],"learn":[174],"discriminative":[175],"word":[178],"generation":[179],"at":[180],"each":[181],"time":[182],"step.":[183],"The":[184],"experimental":[185],"results":[186],"benchmark":[188],"datasets":[189],"demonstrate":[190],"superiority":[192],"our":[194],"method":[195],"compared":[196],"with":[197],"several":[198],"state-of-the-art":[199],"methods.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":36},{"year":2022,"cited_by_count":38},{"year":2021,"cited_by_count":48},{"year":2020,"cited_by_count":28},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}